aredwine3.bsky.social
Graduate Researcher at the University of Nebraska - Lincoln.
7 posts
19 followers
12 following
comment in response to
post
If you can’t back up what you say, maybe you shouldn’t say it? This is @edzitron.com ‘s response to me asking him to verify what he’s saying.
I’m just going to leave this here:
comment in response to
post
I would say yours is in bad faith then. It’s a bit ironic to say my post is when I have given a link to the source and you refuse to produce one, no?
comment in response to
post
Care to share a link to the chat?
comment in response to
post
Hmm, well my output shows the complete opposite of yours when using o1. If we both used o1, I would say a fair conclusion is to always check a model’s output and not blindly trust it.
comment in response to
post
Yes. 01 is their reasoning model.
comment in response to
post
It appears actually using the reasoning model, 01, does much better. See the chat:
chatgpt.com/share/67527c...